shobrook/promptimal
A very fast, very minimal prompt optimizer
Uses a genetic algorithm to iteratively refine prompts by generating candidate variations and scoring them with LLM-as-judge evaluation or custom evaluator functions. Supports hyperparameter tuning (iteration count, population size, termination threshold) and integrates with OpenAI's API by default, with a terminal UI for monitoring optimization progress. Can be extended with custom Python evaluator scripts for dataset-based or task-specific evaluation metrics.
300 stars and 17 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
300
Forks
14
Language
Python
License
MIT
Category
Last pushed
Jan 05, 2025
Monthly downloads
17
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/shobrook/promptimal"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
linshenkx/prompt-optimizer
一款提示词优化器，助力于编写高质量的提示词
Undertone0809/promptulate
🚀Lightweight Large language model automation and Autonomous Language Agents development...
CTLab-ITMO/CoolPrompt
Automatic Prompt Optimization Framework
microsoft/sammo
A library for prompt engineering and optimization (SAMMO = Structure-aware Multi-Objective...
Eladlev/AutoPrompt
A framework for prompt tuning using Intent-based Prompt Calibration